How to Use the Inep Dados Abertos MCP in LangChain

Q: How does LangChain handle large SQL queries from the Inep Dados Abertos MCP Server?

Your agent uses searchdatastoresql to filter data directly on the government servers before pulling it into your chain. This prevents your LangChain application from running out of memory when handling millions of school records.

Q: Can I trace Inep Dados Abertos tool calls in LangChain using LangSmith?

Yes, every call to tools like searchpackages or getresource shows up directly in your LangSmith dashboard. You can inspect the exact SQL queries generated by your LangChain agent and track latency for each request.

Q: How do I handle schema changes in Inep Dados Abertos using LangChain?

Have your LangChain agent call getpackage to inspect the schema before running queries. The agent can dynamically adjust its SQL structure based on the returned metadata, keeping your pipeline resilient.

Run complex educational data pipelines using your LangChain agents to query Brazilian school census and ENEM datasets.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Inep Dados Abertos MCP to LangChain

Create your Vinkius account to connect Inep Dados Abertos to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Inep Dados Abertos with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run SQL Queries on Raw School Data

`search_datastore_sql` lets your LangChain agent run direct SQL queries on raw Brazilian educational databases. Instead of pulling massive datasets into memory, your agent writes precise queries to filter Censo Escolar and ENEM statistics on the fly. That keeps your chain fast and prevents memory overhead during multi-step runs. You can feed these targeted query results directly into subsequent chain steps. If the first step identifies a specific region using `search_packages` with this MCP server, the agent automatically structures a SQL query to pull the exact school-level metrics needed for the next analytical step.

Chain Group and Package Discovery in LangChain

`list_packages` and `get_package` give your LangChain agent the ability to map out the entire structure of INEP's data repository. Your agent inspects available datasets, identifies the correct schemas, and selects the exact resource ID needed for analysis. Manual catalog browsing becomes completely unnecessary before executing a chain. By passing these dataset details to `get_resource`, your chain dynamically adapts to schema changes in Brazilian government data. The agent reads the resource metadata, determines the column structures, and prepares the exact parameters for downstream processing.

Map Organizations and Tags with this MCP Server

`list_organizations` and `list_tags` allow your LangChain agent to categorize Brazilian school datasets by department and theme. Filtering with these tools prevents your agent from processing irrelevant resources. Your resource spend stays low because you only target verified educational metrics. To verify data ownership, your agent can cross-reference these organizations using `get_organization` or `get_group`. Having this context directly in the prompt chain helps the agent make better decisions about which datasets to trust for specific policy analyses.

Setup guide

Set up Inep Dados Abertos MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Inep Dados Abertos tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "inep-dados-abertos-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Inep Dados Abertos transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Inep. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Inep Dados Abertos now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Inep Dados Abertos MCP in LangChain

Your agent uses `search_datastore_sql` to filter data directly on the government servers before pulling it into your chain. This prevents your LangChain application from running out of memory when handling millions of school records.

Yes, every call to tools like `search_packages` or `get_resource` shows up directly in your LangSmith dashboard. You can inspect the exact SQL queries generated by your LangChain agent and track latency for each request.

Have your LangChain agent call `get_package` to inspect the schema before running queries. The agent can dynamically adjust its SQL structure based on the returned metadata, keeping your pipeline resilient.

Yes, you can combine this server with other data sources using the LangChain multi-server adapter. Your agent can query Brazilian school data and merge it with global economic indicators in a single run.

The server runs in an isolated sandbox and only queries public, anonymized educational records from INEP. No personally identifiable student information is ever exposed or transmitted outside your local environment.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript